COR Brief
Image & Video

YOLOv5

YOLOv5 is an open-source computer vision model developed by Ultralytics, implemented in PyTorch, designed for object detection, instance segmentation, and image classification. It processes various input types including URLs, filenames, and image arrays, and outputs detection results in formats such as torch tensors, pandas dataframes, or JSON. The model supports exporting to deployment formats like ONNX, CoreML, and TFLite. YOLOv5 includes multiple model variants, such as the lightweight YOLOv5n (Nano) and instance segmentation models up to version 7.0. It integrates with PyTorch Hub for easy inference and supports datasets in COCO format as well as integrations with platforms like Roboflow and AWS.

Updated Jan 7, 2026open-source

YOLOv5 is a PyTorch-based open-source model for real-time object detection, segmentation, and classification.

Pricing
open-source
Category
Image & Video
Company
Interactive PresentationOpen Fullscreen ↗
01
Performs object detection, instance segmentation, and image classification on images and videos in real-time.
02
Exports models to ONNX, CoreML, TFLite, TensorFlow, and OpenCV DNN formats for deployment across platforms.
03
Supports inference via PyTorch Hub with automatic pretrained model downloads.
04
Accepts inputs like URLs, PIL images, OpenCV images, NumPy arrays, and PyTorch tensors; outputs detections in torch, pandas, or JSON formats.
05
Includes lightweight Nano models (YOLOv5n) and instance segmentation models up to version 7.0.

Real-Time Object Detection

Detect and localize objects in images or video streams for applications such as surveillance or autonomous systems.

Instance Segmentation

Outline precise boundaries of objects within images for detailed analysis in medical imaging or robotics.

Image Classification

Label entire images to categorize content for sorting or filtering in large datasets.

1
Install YOLOv5
Run pip install -U ultralytics ensuring Python >=3.8 and PyTorch >=1.7 are installed.
2
Clone Repository
Clone the GitHub repo with git clone https://github.com/ultralytics/yolov5 and install dependencies using pip install -r requirements.txt.
3
Run Inference
Load a pretrained model via PyTorch Hub using model = torch.hub.load('ultralytics/yolov5', 'yolov5s').
4
Detect Objects
Perform detection on images or videos with results = model('image.jpg').
5
Train Custom Models
Train models using the CLI command yolov5 train --data data.yaml --weights yolov5s.pt.
📊

Strategic Context for YOLOv5

Get weekly analysis on market dynamics, competitive positioning, and implementation ROI frameworks with AI Intelligence briefings.

Try Intelligence Free →
7 days free · No credit card
Pricing
Model: open-source

YOLOv5 is available under the AGPL-3.0 license with no cost for core use. Enterprise licensing is available through Ultralytics.

Assessment
Strengths
  • Easy installation via pip or PyTorch Hub with automatic pretrained model downloads.
  • Supports multiple export formats for deployment across different platforms.
  • Accepts a wide range of input types and outputs results in various data formats.
  • Includes lightweight Nano models suitable for resource-constrained environments.
  • Active development with instance segmentation support introduced in version 7.0.
Limitations
  • Latest updates may not support older custom models like yolov5su without specific commits.
  • Successor YOLOv11 is recommended for access to the newest features and ongoing support.
  • AGPL-3.0 license requires compliance when modifying or distributing the software.